# Workflows for AI video

> **For AI agents:** find the right skill in one call — `curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"` returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the how-to page.

A brief in, a finished video out: UGC ads, product videos, music videos, talking heads, explainers, Shorts and short dramas, step by step, with the models and the edit chosen for you.

**Workflows** is the word 11.0% of tweets about making video use for this kind of thing (“workflow”). Every card here is an agent skill: one install command for Claude Code, Codex, Cursor, OpenClaw or Gemini CLI.

## [AI editing agents](https://varg.ai/how-to/workflows/edit-agents.md) (23)

- [OpenMontage](https://varg.ai/how-to/skills/openmontage.md) — Calesthio: Open-source agentic video studio: 12 pipelines (8 edit your footage), 100+ tools, ~140 skills. Run your agent in it.
- [video-use](https://varg.ai/how-to/skills/video-use.md) — Browser Use: Drop raw takes in a folder, chat with your agent, get final.mp4: transcript-first cuts, grade, subtitles, overlays.
- [FireRed-OpenStoryline](https://varg.ai/how-to/skills/firered-openstoryline.md) — FireRed Team: Conversational editing agent: finds media, writes the storyline, beat-syncs music and refines the cut by chat.
- [ButterCut](https://varg.ai/how-to/skills/buttercut.md) — TubeSalt (barefootford): Claude Code builds selects, scenes and rough cuts from your footage library and exports XML for FCP, Premiere, Resolve.
- [Agentic Video Editor (ave)](https://varg.ai/how-to/skills/agentic-video-editor.md) — poseljacob: CLI where Gemini agents pick shots, trim, render with FFmpeg and score the result until a brief is met.
- [OpenChatCut](https://varg.ai/how-to/skills/openchatcut.md) — 0xsline: Local-first chat video editor with a multi-track timeline that Codex and Claude Code can edit over MCP.
- [BaoCut](https://varg.ai/how-to/skills/baocut.md) — Jim Liu: Desktop AI video agent that transcribes, subtitles, translates, dubs, cuts and animates into an editable timeline.
- [CartCut](https://varg.ai/how-to/skills/cartcut.md) — Cartesian: Layer-based video editor built for AI agents, with a Claude Code plugin, skill and MCP server.
- [Hypit](https://varg.ai/how-to/skills/hypit.md) — Hypit: Clone a viral video as a word-anchored workflow: swap face, words and B-roll, then ship many variants.
- [claude-youtube-editor](https://varg.ai/how-to/skills/claude-youtube-editor.md) — Hasan Aboul Hasan: Record a talking head; Claude Code does the cut, Remotion visuals, voice, SFX, thumbnail and YouTube upload.
- [ghost-editor](https://varg.ai/how-to/skills/ghost-editor.md) — kurbaitaev: Talking-head reel editor in your agent: best takes, face-safe word captions, motion graphics, 7 styles.
- [SeeCut](https://varg.ai/how-to/skills/seecut.md) — YeJe-cpu: Talking-head and AI-avatar fine cut that watches its own render with Gemini and iterates up to three versions.
- [Oh My Cassette](https://varg.ai/how-to/skills/oh-my-cassette.md) — Cassette: MCP bridge to the Cassette editing agent: import footage and music, brief a montage, revise and export.
- [Video Recap Skills](https://varg.ai/how-to/skills/video-recap-skills.md) — Zenstory: Seven skills that cut one or more videos into a narrated recap: scene detection, ASR, VLM, script, TTS, ffmpeg.
- [Erduo B-roll Loop Engineering](https://varg.ai/how-to/skills/erduo-broll-loop.md) — erduo1998-cell: SRT-driven B-roll agent: a Director plans shots, Creators build them in HyperFrames or Remotion, a Reviewer checks.
- [Concat](https://varg.ai/how-to/skills/concat.md) — jub0t: Free, local-first CapCut replacement with a built-in MCP server and JSON-RPC API so agents can cut video.
- [OpenMontage Talking Head](https://varg.ai/how-to/skills/openmontage-talking-head.md) — Calesthio: Takes raw footage of a person speaking, transcribes it, makes edit decisions (fillers, dead air, pacing), adds subtitles
- [OpenMontage Clip Factory](https://varg.ai/how-to/skills/openmontage-clip-factory.md) — Calesthio: Extracts a batch of ranked short clips from one long source (webinar, stream, talk, interview) with gates for clip selec
- [OpenMontage Podcast Repurpose](https://varg.ai/how-to/skills/openmontage-podcast-repurpose.md) — Calesthio: Turns podcast audio or video into audiogram or caption-led clips, quote cards and an optional full-episode companion vid
- [OpenMontage Hybrid](https://varg.ai/how-to/skills/openmontage-hybrid.md) — Calesthio: Combines your source footage with designed or generated support visuals (diagrams, overlays, inserts) with gates for sou
- [OpenMontage Screen Demo](https://varg.ai/how-to/skills/openmontage-screen-demo.md) — Calesthio: Polishes real screen captures into demos with callouts, zoom crops, subtitles and cleaned audio, or renders a synthetic 
- [OpenMontage Documentary Montage](https://varg.ai/how-to/skills/openmontage-documentary-montage.md) — Calesthio: Builds a CLIP-searchable corpus from free archives (Pexels, Archive.org, NASA, Wikimedia, Unsplash) and cuts real footag
- [OpenMontage Cinematic](https://varg.ai/how-to/skills/openmontage-cinematic.md) — Calesthio: Mood-led trailers, teasers and brand films, best with supplied footage; can analyze a reference video and fill gaps with

## [Ads & UGC](https://varg.ai/how-to/workflows/ads.md) (7)

- [fal Marketing](https://varg.ai/how-to/skills/fal-marketing.md) — fal: Produce campaign asset matrices: launch kits, paid-social variants, banners and channel deliverables.
- [fal UGC](https://varg.ai/how-to/skills/fal-ugc.md) — fal: Script and generate UGC-style creator ads: talking heads, demos, testimonials, unboxings and reactions.
- [AI Marketing Videos](https://varg.ai/how-to/skills/inference-sh-ai-marketing-videos.md) — inference.sh: Make product demos, promos, testimonials and launch videos with Veo, Seedance, Wan, FLUX and Kokoro.
- [FLUX 3 Product Ads](https://varg.ai/how-to/skills/flux-3-product-ads.md) — Black Forest Labs: Build a finished product ad with FLUX 3: shot design, voiceover sync, deterministic assembly, QC gates.
- [Krea Marketing](https://varg.ai/how-to/skills/krea-marketing.md) — Krea: Make performance marketing creative on Krea: packshots, marketplace cards, UGC and video ads, Meta Ads.
- [Marketing Video Production](https://varg.ai/how-to/skills/marketingskills-video.md) — Corey Haines: Corey Haines' marketing video skill: pick code, a video model or an avatar, then script, prompt and repurpose.
- [Business Motion Film](https://varg.ai/how-to/skills/business-motion-film.md) — echris6: Premium short commercials for real businesses: storyboard first, HTML/GSAP motion and an independent-critic loop.

## [Product videos](https://varg.ai/how-to/workflows/product.md) (6)

- [Higgsfield Marketplace Cards](https://varg.ai/how-to/skills/higgsfield-marketplace-cards.md) — Higgsfield: Produce marketplace listing images: a compliant main image, secondary shots and A+ content modules.
- [Higgsfield Product Photoshoot](https://varg.ai/how-to/skills/higgsfield-product-photoshoot.md) — Higgsfield: Shoot brand-quality product images in 10 modes: studio, lifestyle, hero banners, ad packs, try-on and more.
- [fal Commercial](https://varg.ai/how-to/skills/fal-commercial.md) — fal: Plan and run product photography, e-commerce batches, product reveal videos and lifestyle commercials.
- [AI Product Photography](https://varg.ai/how-to/skills/inference-sh-ai-product-photography.md) — inference.sh: Generate commercial product shots, lifestyle scenes and mockups with FLUX, Imagen 3, Grok and Seedream.
- [ASO App Store Screenshots](https://varg.ai/how-to/skills/aso-appstore-screenshots.md) — Adam Lyttle: App Store screenshots from your codebase: finds the core benefits, pairs simulator shots, then composes and enhances.
- [E-commerce Image Studio](https://varg.ai/how-to/skills/ecom-image2.md) — buluslan: 39 e-commerce image templates (main images, lifestyle, A+, sizes, GIFs) with one style lock across a campaign set.

## [Explainers](https://varg.ai/how-to/workflows/explainers.md) (5)

- [HyperFrames Slideshow](https://varg.ai/how-to/skills/hyperframes-slideshow.md) — HeyGen: Build a live, navigable deck with fragment reveals, branching hotspots and presenter notes instead of an MP4.
- [Plain-Sight Explainer](https://varg.ai/how-to/skills/hyperframes-vox-explainer.md) — HeyGen: 60–90 s collage explainers about everyday things, or mined from your documents and links, with numeric seam checks.
- [Higgsfield Video Explainer](https://varg.ai/how-to/skills/higgsfield-video-explainer.md) — Higgsfield: Turn a topic or document into a narrated, stylized explainer assembled from 10-second voiced blocks.
- [Explainroo](https://varg.ai/how-to/skills/explainroo.md) — Vincent Schmalbach: Narrated explainer MP4s with a local voice (Kokoro), word timing (Whisper) and a canvas renderer; no API key needed.
- [Manim Skills (3Blue1Brown Style)](https://varg.ai/how-to/skills/manim-skill.md) — Adithya S K: Plan and code 3Blue1Brown-style math animations: a scene composer plus ManimCE and ManimGL best practices.

## [Talking heads & avatars](https://varg.ai/how-to/workflows/talking-head.md) (5)

- [Character Keynote](https://varg.ai/how-to/skills/varg-character-keynote.md) — varg, beta: One render call: a Soul character delivers a keynote-style ad line on a generated stage, voiced by Seedance 2.5.
- [Turn a script into a two-person podcast video](https://varg.ai/how-to/skills/varg-podcast-video.md) — varg, beta: Two-character podcast or debate clips: one studio set, locked camera angles, MiniMax H3 Max with native audio.
- [Talking Head Production](https://varg.ai/how-to/skills/inference-sh-talking-head-production.md) — inference.sh: Produce talking-head videos with AI avatars, lip-sync and voiceover, from portrait specs to final cut.
- [AI Podcast Video](https://varg.ai/how-to/skills/inference-sh-ai-podcast.md) — inference.sh: Generate a multi-person talking-head podcast video from scratch: characters, voices, avatars, stitching.
- [Lanshu AI Presenter Video](https://varg.ai/how-to/skills/lanshu-ai-presenter-video.md) — Lanshu: Publish-ready explainers led by an AI presenter from an authorized photo, or in one of twelve presenter-free styles.

## [Stories & short dramas](https://varg.ai/how-to/workflows/story.md) (4)

- [Shuohao Short-Drama Skills](https://varg.ai/how-to/skills/shuohao-short-drama.md) — Wesley Wang: Seven chained skills from novel to AI short drama: characters, outline, art bible, script, staging, storyboard.
- [AI Short Drama Studio](https://varg.ai/how-to/skills/ai-short-drama-studio.md) — Hao0321: Greenlight score, series bible, episode compiler and production pack for serialized AI short dramas and manju.
- [Baidu Wenku AI Picture Book](https://varg.ai/how-to/skills/ai-picture-book.md) — ide-rea, beta: Turns a story text into a static or animated picture-book video through Baidu Wenku
- [dLazy Image Storyboard](https://varg.ai/how-to/skills/dlazy-image-storyboard.md) — dlazyai, beta: Plan-first storyboard workflow: specs, character sheet and script approved before each panel is rendered

## [Shorts & Reels](https://varg.ai/how-to/workflows/shorts.md) (3)

- [AI Social Media Content](https://varg.ai/how-to/skills/inference-sh-ai-social-media-content.md) — inference.sh: Produce reels, shorts, images and thumbnails for TikTok, Instagram, YouTube and X with one toolkit.
- [Krea Faceless Video](https://varg.ai/how-to/skills/krea-faceless-video.md) — Krea: Make narrated faceless explainers, documentaries and kids' stories as finished multi-scene films on Krea.
- [Video Producer](https://varg.ai/how-to/skills/video-producer.md) — a1024708231, beta: Topic in, narrated short MP4 out: shot plan, AI stills, per-scene voiceover, Remotion render

## [Animation & motion graphics](https://varg.ai/how-to/workflows/animation.md) (3)

- [Day in My Life](https://varg.ai/how-to/skills/hyperframes-day-in-my-life.md) — HeyGen: A 60–75 s hand-drawn ink film of your agent's day with you, built from local Claude Code history, scored for strings.
- [Session Story](https://varg.ai/how-to/skills/hyperframes-session-story.md) — HeyGen: A 40–70 s watercolor film of a typical session with your agent, told in your real messages, with its own score.
- [Story to Hand-drawn Video](https://varg.ai/how-to/skills/story-to-handdrawn-video.md) — gnipbao: Chinese stories or ordered images into silent hand-drawn diary-comic animations, with a curated 30-style menu.

## [Music videos](https://varg.ai/how-to/workflows/music.md) (3)

- [Turn a song into an AI music video](https://varg.ai/how-to/skills/varg-music-video.md) — varg, beta: Direct an AI music video the way top X creators do: song map, beat-grid storyboard, stills first, Seedance, lip-sync.
- [Prod by Claude](https://varg.ai/how-to/skills/hyperframes-prod-by-claude.md) — HeyGen: A square video of a Strudel live-coding track where every code token lights up on the note it plays.
- [Motion Graphics Music Video](https://varg.ai/how-to/skills/motion-graphics-music-video.md) — Francesco Canessa: Animated character music videos from your song and a prompt: storyboard, fal generation, p5 motion graphics, VFX.

## [Editing & clips](https://varg.ai/how-to/workflows/editing.md) (3)

- [Chengfeng Videocut](https://varg.ai/how-to/skills/chengfeng-videocut.md) — chengfeng: Chinese talking-head editing: word-level transcript, five-pass flub sweep, human review in a Studio, subtitles, export.
- [Claude Code Video Toolkit](https://varg.ai/how-to/skills/claude-code-video-toolkit.md) — Digital Samba: Open-source video workspace for Claude Code: script, voice, music, visuals and Remotion render on your own GPU account.
- [Herk Edit Kit](https://varg.ai/how-to/skills/herk-edit-kit.md) — Nate Herk: Nate Herk's kit to edit talking-head videos, reels and Shorts: silence and flub cuts, storytelling, motion graphics.

## [Images & thumbnails](https://varg.ai/how-to/workflows/image.md) (3)

- [Higgsfield YouTube Thumbnail](https://varg.ai/how-to/skills/higgsfield-youtube-thumbnail.md) — Higgsfield: Design truthful, high-CTR YouTube thumbnails and vertical covers with up to three consistent faces.
- [Slack GIF Creator](https://varg.ai/how-to/skills/anthropic-slack-gif-creator.md) — Anthropic: Make animated GIFs that pass Slack's limits: 128×128 emoji or 480×480 message GIFs, validated on export.
- [Baoyu Cover Image](https://varg.ai/how-to/skills/baoyu-cover-image.md) — Jim Liu: Article cover images built from five dimensions (type, palette, rendering, text, mood) in 2.35:1, 16:9 or 1:1.

## [Cinematic & short films](https://varg.ai/how-to/workflows/cinematic.md) (2)

- [Previz to Seedance](https://varg.ai/how-to/skills/varg-previz.md) — varg, beta: Plan multi-shot AI video before paying: story, anchor sheets, a three.js grey-box previz, then a Seedance v2v pack.
- [fal Recipes](https://varg.ai/how-to/skills/fal-recipes.md) — fal: Follow proven multi-step fal pipelines for commercials, product shots, characters, lip-sync and try-on.

## [Launch videos](https://varg.ai/how-to/workflows/launch.md) (2)

- [Onetake](https://varg.ai/how-to/skills/onetake.md) — Patrick: Launch films that never cut to the next slide: one continuous camera, measured moves, motion blur, a slideshow oracle.
- [Guizang Product Video](https://varg.ai/how-to/skills/guizang-product-video.md) — Guizang: Software promos and release-notes videos built from your real product components, with original music and SFX.

## [Phone & app screens](https://varg.ai/how-to/workflows/native-ui.md) (2)

- [iMessage Video](https://varg.ai/how-to/skills/varg-imessage-video.md) — varg, beta: Pixel-perfect iMessage conversation videos from a JSON script: iOS 26 chrome, typing, tapbacks, group chats.
- [Gooseworks Video (Apple Notes Ads)](https://varg.ai/how-to/skills/gooseworks-apple-notes-ads.md) — Gooseworks: Video ads in chat from a reference ad or a ready style, including the viral HTML-only Apple Notes typing ad.

## [Logo animations & intros](https://varg.ai/how-to/workflows/brand-motion.md) (1)

- [HyperFrames Figma](https://varg.ai/how-to/skills/hyperframes-figma.md) — HeyGen: Turn a Figma link into video: rendered assets, brand tokens, components and storyboard frames rebuilt as motion.

## [3D scenes](https://varg.ai/how-to/workflows/3d-scenes.md) (1)

- [Procedural 3D Story](https://varg.ai/how-to/skills/karpathy-3d-story.md) — chencheng (云谦), beta: Turn a myth or book into a seeded, multi-chapter procedural three.js film in one scene.html, audited frame by frame.

## [Characters](https://varg.ai/how-to/workflows/characters.md) (1)

- [Consistent Characters](https://varg.ai/how-to/skills/varg-consistent-characters.md) — varg, beta: Multi-scene ads where the same actors, outfits and location hold in every cut: cards, composites, Kling v3 clips.

## [Logos & brand kits](https://varg.ai/how-to/workflows/logos.md) (1)

- [Higgsfield Brandkit](https://varg.ai/how-to/skills/higgsfield-brandkit.md) — Higgsfield: Build a complete visual identity: palette, SVG logo marks, type, mockups, packaging and an editable brandbook.

## [Lyrics & songwriting](https://varg.ai/how-to/workflows/lyrics.md) (1)

- [Bitwize Music (Suno Album Studio)](https://varg.ai/how-to/skills/bitwize-music.md) — bitwize-music-studio: A 53-skill Claude Code plugin for human + AI albums on Suno: lyrics, style prompts, stem mixing, mastering, release.

## [Voice & voiceover](https://varg.ai/how-to/workflows/audio.md) (1)

- [AI Podcast Creation](https://varg.ai/how-to/skills/inference-sh-ai-podcast-creation.md) — inference.sh: Produce audio podcasts and audiobooks with multi-voice TTS, music beds, intros, outros and ffmpeg.

## [Tools & renderers](https://varg.ai/how-to/workflows/tooling.md) (1)

- [AI Content Pipeline](https://varg.ai/how-to/skills/inference-sh-ai-content-pipeline.md) — inference.sh: Chain image, video, voice and music models into one pipeline: generate, animate, voice over, merge.

## Other kinds of skills

- [Prompts](https://varg.ai/how-to/prompts.md): The words a video model obeys: camera angles, shot sizes, lighting, characters, hooks and prompt guides for Seedance, Kling, Veo, FLUX and Higgsfield. Your agent writes the prompt with them, or you paste them into the model.
- [Effects](https://varg.ai/how-to/effects.md): An effect you can see, added to your video: animated titles, captions, transitions, shader backgrounds, logo animations, device mockups and viral camera tricks. Hand your agent the footage or the brief and get the effect.
- [Styles](https://varg.ai/how-to/styles.md): The look of the whole video: art styles, film looks, color grades and LUTs, caption fonts and style references. Pick a style and every shot your agent makes follows it.
- [Guides](https://varg.ai/how-to/guides.md): Know-how your agent reads before it works: how to write a script, storyboard, edit and caption, and how to use Remotion, HyperFrames, GSAP, Three.js and FFmpeg.
- [Models & tools](https://varg.ai/how-to/models.md): Run one model or tool from your agent: Seedance, Veo, Kling, FLUX, GPT Image, Nano Banana, ElevenLabs and 1,200+ more, plus scrapers, trend search and video analysis.

## Questions

**What is an AI video workflow skill?**

A skill that takes a brief to a finished video step by step: script, shots, generation, voice, music, edit and captions, with the models chosen for you.

**Which workflows are there?**

UGC and performance ads, product videos, music videos, talking heads and podcasts, explainers, Shorts and Reels, launch videos and short dramas.